471a81b5e7
CI / Format (ruff format) (push) Successful in 26s
CI / Lint (ruff check) (push) Successful in 27s
CI / Sync project version with tag (push) Has been skipped
CI / Type check (ty) (push) Successful in 37s
CI / Lint (ruff check) (pull_request) Successful in 36s
CI / Format (ruff format) (pull_request) Successful in 31s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Type check (ty) (pull_request) Successful in 33s
CI / Tests (push) Successful in 1m43s
CI / Tests (pull_request) Successful in 1m39s
Lets the vocab maps, event-id split index, and normalizer stats be warmed once for a dataset (right after `dwarf convert`, or before a `dwarf hparam-scan` sweep) without needing to also start training. Extracts the setup-stage logic out of giant/pipeline.py:run_train_job into a standalone run_setup_stage() (returning a SetupStageResult), reused by both run_train_job and the new dwarf command's scripts/warm_setup_cache.py — a behavior-preserving refactor, covered by the existing test_pipeline.py suite. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
149 lines
4.9 KiB
Python
149 lines
4.9 KiB
Python
from typer.testing import CliRunner
|
|
|
|
from giant.data import setup_cache
|
|
from scripts.dwarf import app
|
|
from test_pipeline import _make_synthetic_steps
|
|
|
|
runner = CliRunner()
|
|
|
|
|
|
def test_convert_rejects_jobs_below_one(tmp_path):
|
|
root_file = tmp_path / "shard.root"
|
|
root_file.touch()
|
|
result = runner.invoke(app, ["convert", str(root_file), "--jobs", "0"])
|
|
assert result.exit_code != 0
|
|
assert "--jobs must be >= 1" in result.output
|
|
|
|
|
|
def test_convert_rejects_output_with_multiple_files(tmp_path):
|
|
a = tmp_path / "a.root"
|
|
b = tmp_path / "b.root"
|
|
a.touch()
|
|
b.touch()
|
|
result = runner.invoke(app, ["convert", str(a), str(b), "--output", "out.parquet"])
|
|
assert result.exit_code != 0
|
|
assert "--output can only be used with a single input file" in result.output
|
|
|
|
|
|
def test_convert_rejects_output_with_parallel_jobs(tmp_path):
|
|
root_file = tmp_path / "shard.root"
|
|
root_file.touch()
|
|
result = runner.invoke(
|
|
app, ["convert", str(root_file), "--output", "out.parquet", "--jobs", "2"]
|
|
)
|
|
assert result.exit_code != 0
|
|
assert "--output cannot be combined with --jobs > 1" in result.output
|
|
|
|
|
|
def test_convert_default_jobs_is_one():
|
|
result = runner.invoke(app, ["convert", "--help"])
|
|
assert result.exit_code == 0
|
|
assert "default: 1" in result.output
|
|
|
|
|
|
def test_bump_gen_requires_reason():
|
|
result = runner.invoke(app, ["bump-gen"])
|
|
assert result.exit_code != 0
|
|
assert "reason" in result.output.lower()
|
|
|
|
|
|
def test_create_manifest_requires_exactly_one_of_output_or_pool(tmp_path):
|
|
f = tmp_path / "a.parquet"
|
|
f.touch()
|
|
result = runner.invoke(app, ["create-manifest", str(f)])
|
|
assert result.exit_code != 0
|
|
assert "exactly one of --output or --pool is required" in result.output
|
|
|
|
|
|
def test_create_manifest_requires_type_with_pool(tmp_path):
|
|
f = tmp_path / "a.parquet"
|
|
f.touch()
|
|
result = runner.invoke(app, ["create-manifest", "--pool", "pbwo4", str(f)])
|
|
assert result.exit_code != 0
|
|
assert "--type is required when --pool is given" in result.output
|
|
|
|
|
|
def test_status_reports_missing_root(tmp_path):
|
|
missing = tmp_path / "does-not-exist"
|
|
result = runner.invoke(app, ["status", "--root", str(missing)])
|
|
assert result.exit_code != 0
|
|
assert "is not a directory" in result.output
|
|
|
|
|
|
def test_warm_cache_writes_sidecar(tmp_path):
|
|
data = _make_synthetic_steps(tmp_path / "data.parquet", n_events=20)
|
|
|
|
result = runner.invoke(app, ["warm-cache", str(data)])
|
|
|
|
assert result.exit_code == 0, result.output
|
|
loaded = setup_cache.load(data, [data])
|
|
assert loaded is not None
|
|
assert loaded.vocab is not None
|
|
assert loaded.event_index is not None
|
|
assert "valfrac=0.1_seed=0_cond=physical" in loaded.normalizers
|
|
|
|
|
|
def test_warm_cache_second_run_hits_cache(tmp_path):
|
|
data = _make_synthetic_steps(tmp_path / "data.parquet", n_events=20)
|
|
runner.invoke(app, ["warm-cache", str(data)])
|
|
|
|
result = runner.invoke(app, ["warm-cache", str(data)])
|
|
|
|
assert result.exit_code == 0, result.output
|
|
assert "event index: cache hit" in result.output
|
|
assert "vocabulary maps: cache hit" in result.output
|
|
assert "normalizer: cache hit" in result.output
|
|
|
|
|
|
def test_warm_cache_router_process_warms_proc_map(tmp_path):
|
|
data = _make_synthetic_steps(tmp_path / "data.parquet", n_events=20)
|
|
|
|
result = runner.invoke(
|
|
app,
|
|
[
|
|
"warm-cache",
|
|
str(data),
|
|
"--router",
|
|
"--router-type",
|
|
"process",
|
|
"--n-experts",
|
|
"3",
|
|
],
|
|
)
|
|
|
|
assert result.exit_code == 0, result.output
|
|
loaded = setup_cache.load(data, [data])
|
|
assert loaded is not None
|
|
assert 3 in loaded.proc_maps
|
|
|
|
|
|
def test_warm_cache_rebuild_ignores_existing(tmp_path):
|
|
data = _make_synthetic_steps(tmp_path / "data.parquet", n_events=20)
|
|
files = [data]
|
|
stale = setup_cache.SetupCache.empty(files)
|
|
stale.vocab = ({999999: 0}, {"G4_AIR": 0}) # deliberately wrong
|
|
setup_cache.save(data, files, stale)
|
|
|
|
result = runner.invoke(app, ["warm-cache", str(data), "--rebuild"])
|
|
|
|
assert result.exit_code == 0, result.output
|
|
loaded = setup_cache.load(data, files)
|
|
assert loaded is not None
|
|
assert loaded.vocab is not None
|
|
assert set(loaded.vocab[0].keys()) == {11, 22}
|
|
|
|
|
|
def test_warm_cache_different_val_fraction_is_separate_entry(tmp_path):
|
|
data = _make_synthetic_steps(tmp_path / "data.parquet", n_events=20)
|
|
runner.invoke(app, ["warm-cache", str(data), "--val-fraction", "0.1"])
|
|
|
|
result = runner.invoke(app, ["warm-cache", str(data), "--val-fraction", "0.3"])
|
|
|
|
assert result.exit_code == 0, result.output
|
|
assert "vocabulary maps: cache hit" in result.output
|
|
assert "fitting normalizer (streaming)" in result.output
|
|
loaded = setup_cache.load(data, [data])
|
|
assert loaded is not None
|
|
assert "valfrac=0.1_seed=0_cond=physical" in loaded.normalizers
|
|
assert "valfrac=0.3_seed=0_cond=physical" in loaded.normalizers
|